mirror of
https://git.postgresql.org/git/postgresql.git
synced 2026-02-13 18:07:05 +08:00
afdfcd3f76
Revert our previous addition of "all" flags to copyins() and copyouts(); they're no longer needed, and were never anything but an unsightly hack. Improve a couple of infelicities in the REG_DEBUG code for dumping the NFA data structure, including adding code to count the total number of states and arcs. Add a couple of missed error checks. Add some more documentation in the README file, and some regression tests illustrating cases that exceeded the state-count limit and/or took unreasonable amounts of time before this set of patches. Back-patch to all supported branches.
84 lines
3.1 KiB
SQL
84 lines
3.1 KiB
SQL
--
|
|
-- Regular expression tests
|
|
--
|
|
|
|
-- Don't want to have to double backslashes in regexes
|
|
set standard_conforming_strings = on;
|
|
|
|
-- Test simple quantified backrefs
|
|
select 'bbbbb' ~ '^([bc])\1*$' as t;
|
|
select 'ccc' ~ '^([bc])\1*$' as t;
|
|
select 'xxx' ~ '^([bc])\1*$' as f;
|
|
select 'bbc' ~ '^([bc])\1*$' as f;
|
|
select 'b' ~ '^([bc])\1*$' as t;
|
|
|
|
-- Test quantified backref within a larger expression
|
|
select 'abc abc abc' ~ '^(\w+)( \1)+$' as t;
|
|
select 'abc abd abc' ~ '^(\w+)( \1)+$' as f;
|
|
select 'abc abc abd' ~ '^(\w+)( \1)+$' as f;
|
|
select 'abc abc abc' ~ '^(.+)( \1)+$' as t;
|
|
select 'abc abd abc' ~ '^(.+)( \1)+$' as f;
|
|
select 'abc abc abd' ~ '^(.+)( \1)+$' as f;
|
|
|
|
-- Test some cases that crashed in 9.2beta1 due to pmatch[] array overrun
|
|
select substring('asd TO foo' from ' TO (([a-z0-9._]+|"([^"]+|"")+")+)');
|
|
select substring('a' from '((a))+');
|
|
select substring('a' from '((a)+)');
|
|
|
|
-- Test conversion of regex patterns to indexable conditions
|
|
explain (costs off) select * from pg_proc where proname ~ 'abc';
|
|
explain (costs off) select * from pg_proc where proname ~ '^abc';
|
|
explain (costs off) select * from pg_proc where proname ~ '^abc$';
|
|
explain (costs off) select * from pg_proc where proname ~ '^abcd*e';
|
|
explain (costs off) select * from pg_proc where proname ~ '^abc+d';
|
|
explain (costs off) select * from pg_proc where proname ~ '^(abc)(def)';
|
|
explain (costs off) select * from pg_proc where proname ~ '^(abc)$';
|
|
explain (costs off) select * from pg_proc where proname ~ '^(abc)?d';
|
|
|
|
-- Test for infinite loop in pullback() (CVE-2007-4772)
|
|
select 'a' ~ '($|^)*';
|
|
|
|
-- These cases expose a bug in the original fix for CVE-2007-4772
|
|
select 'a' ~ '(^)+^';
|
|
select 'a' ~ '$($$)+';
|
|
|
|
-- More cases of infinite loop in pullback(), not fixed by CVE-2007-4772 fix
|
|
select 'a' ~ '($^)+';
|
|
select 'a' ~ '(^$)*';
|
|
select 'aa bb cc' ~ '(^(?!aa))+';
|
|
select 'aa x' ~ '(^(?!aa)(?!bb)(?!cc))+';
|
|
select 'bb x' ~ '(^(?!aa)(?!bb)(?!cc))+';
|
|
select 'cc x' ~ '(^(?!aa)(?!bb)(?!cc))+';
|
|
select 'dd x' ~ '(^(?!aa)(?!bb)(?!cc))+';
|
|
|
|
-- Test for infinite loop in fixempties() (Tcl bugs 3604074, 3606683)
|
|
select 'a' ~ '((((((a)*)*)*)*)*)*';
|
|
select 'a' ~ '((((((a+|)+|)+|)+|)+|)+|)';
|
|
|
|
-- These cases used to give too-many-states failures
|
|
select 'x' ~ 'abcd(\m)+xyz';
|
|
select 'a' ~ '^abcd*(((((^(a c(e?d)a+|)+|)+|)+|)+|a)+|)';
|
|
select 'x' ~ 'a^(^)bcd*xy(((((($a+|)+|)+|)+$|)+|)+|)^$';
|
|
select 'x' ~ 'xyz(\Y\Y)+';
|
|
select 'x' ~ 'x|(?:\M)+';
|
|
|
|
-- This generates O(N) states but O(N^2) arcs, so it causes problems
|
|
-- if arc count is not constrained
|
|
select 'x' ~ repeat('x*y*z*', 1000);
|
|
|
|
-- Test backref in combination with non-greedy quantifier
|
|
-- https://core.tcl.tk/tcl/tktview/6585b21ca8fa6f3678d442b97241fdd43dba2ec0
|
|
select 'Programmer' ~ '(\w).*?\1' as t;
|
|
select regexp_matches('Programmer', '(\w)(.*?\1)', 'g');
|
|
|
|
-- Test for proper matching of non-greedy iteration (bug #11478)
|
|
select regexp_matches('foo/bar/baz',
|
|
'^([^/]+?)(?:/([^/]+?))(?:/([^/]+?))?$', '');
|
|
|
|
-- Test for infinite loop in cfindloop with zero-length possible match
|
|
-- but no actual match (can only happen in the presence of backrefs)
|
|
select 'a' ~ '$()|^\1';
|
|
select 'a' ~ '.. ()|\1';
|
|
select 'a' ~ '()*\1';
|
|
select 'a' ~ '()+\1';
|